☆ 4.6 Article

Dynamic Offloading Loading Optimization in Distributed Fault Diagnosis System with Deep Reinforcement Learning Approach

APPLIED SCIENCES-BASEL (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Theory & Methods

Online computation offloading with double reinforcement learning algorithm in mobile edge computing

Linbo Liao et al.

Summary: This paper discusses a mobile edge computing system with a server and multiple mobile devices that need to perform computation tasks with priorities. By providing computational support, mobile edge computing solves the problem of limited computing power and battery capacity of mobile devices. To minimize delay and energy consumption in the long term, an online algorithm called the double reinforcement learning computation offloading (DRLCO) algorithm is proposed.

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING (2023)

Add to Collection

Article Engineering, Multidisciplinary

Secure Transmission for Multi-UAV-Assisted Mobile Edge Computing Based on Reinforcement Learning

Weidang Lu et al.

Summary: This paper proposes two secure transmission methods for multi-UAV-assisted mobile edge computing based on single-agent and multi-agent reinforcement learning, respectively. The deployment of UAVs is optimized using the spiral placement algorithm, and secure offloading is optimized using reinforcement learning to maximize system utility. Simulation results show that compared to the single-agent method and the benchmark, the multi-agent method can optimize offloading better and achieve larger system utility.

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

Anti-noise diesel engine misfire diagnosis using a multi-scale CNN-LSTM neural network with denoising module

Chengjin Qin et al.

Summary: A novel multi-scale CNN-LSTM neural network (MSCNN-LSTMNet) with a residual-CNN denoising module is proposed for anti-noise diesel engine misfire diagnosis. MSCNN-LSTMNet achieves better anti-noise and generalisation performances by utilizing multi-scale feature extraction and sequential feature extraction. Experimental results demonstrate the effectiveness of MSCNN-LSTMNet in various noise levels and working conditions.

CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY (2023)

Add to Collection

Article Engineering, Electrical & Electronic

Distributed Machine Learning for Multiuser Mobile Edge Computing Systems

Yinghao Guo et al.

Summary: This paper investigates a distributed machine learning approach for a multiuser mobile edge computing network in a cognitive eavesdropping environment. By optimizing the offloading ratio, bandwidth, and computational capability allocation ratio, the proposed method effectively reduces system costs and ensures more resources are allocated to users with higher task priorities.

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING (2022)

Add to Collection

Article Engineering, Mechanical

Multi-source transfer learning network to complement knowledge for intelligent diagnosis of machines with unseen faults

Bin Yang et al.

Summary: Current successes in deep transfer learning-based fault diagnosis often rely on assumptions that may not hold true in engineering scenarios. Thus, a framework called a multi-source transfer learning network has been proposed to address issues such as uncovering all fault types of target machines and imbalanced target samples.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2022)

Add to Collection

Article Engineering, Mechanical

Semi-supervised hierarchical attribute representation learning via multi-layer matrix factorization for machinery fault diagnosis

Xu Wang et al.

Summary: A novel semi-supervised multi-layer non-negative matrix factorization method is proposed in this study for fault diagnosis, which learns hierarchical attribute representations of different fault locations and sizes from the time-frequency distribution of signals and uses semi-supervised learning to improve fault diagnosis accuracy. Experiments in aeroengine bearings and a diesel engine demonstrate the feasibility and superiority of the proposed method.

MECHANISM AND MACHINE THEORY (2022)

Add to Collection

Article Computer Science, Hardware & Architecture

Survey on computation offloading in UAV-Enabled mobile edge computing

S. M. Asiful Huda et al.

Summary: With the increasing growth of IoT devices, effective computation performance has become critical. Mobile edge computing (MEC) and unmanned aerial vehicles (UAVs) can address this issue. However, communication overhead and delays are major challenges. This study reviews UAV-enabled MEC solutions focusing on offloading and compares algorithms for their features and performance. Additionally, open issues and research challenges in design and implementation are discussed.

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS (2022)

Add to Collection

Article Engineering, Mechanical

A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: Theories, applications and challenges

Weihua Li et al.

Summary: Deep Transfer Learning combines the advantages of Deep Learning in feature representation and Transfer Learning in knowledge transfer, making DL-based fault diagnosis methods more reliable and robust. However, further research is needed to explore the potential of DTL-based approaches in Intelligent Fault Diagnosis.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2022)

Add to Collection

Article Engineering, Mechanical

Residual deep subdomain adaptation network: A new method for intelligent fault diagnosis of bearings across multiple domains

Zuoyi Chen et al.

Summary: The proposed residual deep subdomain adaptation network allows for intelligent fault diagnosis across multiple domains with only one transfer task needed, regardless of changing operating conditions. It accurately aligns the distribution of related subdomains within the source and target domains using local maximum mean discrepancy.

MECHANISM AND MACHINE THEORY (2022)

Add to Collection

Article Chemistry, Multidisciplinary

Competing Miners: A Synergetic Solution for Combining Blockchain and Edge Computing in Unmanned Aerial Vehicle Networks

Jacob Mathias Nilsen et al.

Summary: Edge computing is highly promising for UAV applications, and integrating blockchain technology can enhance privacy protection and data integrity. However, the computational demands of blockchain pose challenges for UAVs. This article proposes a synergetic solution using competing miners in a blockchain, presenting two novel frameworks that effectively address critical limitations. The goal is to reduce mining time and energy consumption for edge computing. The article covers the fundamentals of blockchain with competing miners, describes the proposed frameworks with experimental results, and discusses application scenarios, technical challenges, and future research directions.

APPLIED SCIENCES-BASEL (2022)

Add to Collection

Article Chemistry, Multidisciplinary

Rolling Bearing Weak Fault Feature Extraction under Variable Speed Conditions via Joint Sparsity and Low-Rankness in the Cyclic Order-Frequency Domain

Ran Wang et al.

Summary: Rolling bearings are crucial in mechanical systems and extracting weak fault features with time-varying speed is essential for mechanical system diagnosis. This paper proposes a method that computes order-frequency spectral correlation to transform the measured signal and applies joint sparsity and low-rankness constraint to detect time-varying faulty characteristics. An algorithm in the ADMM framework is derived and the enhanced envelope order spectrum is used to further detect defective features.

APPLIED SCIENCES-BASEL (2022)

Add to Collection

Article Computer Science, Information Systems

Adaptive Privacy-Preserving Federated Learning for Fault Diagnosis in Internet of Ships

Zehui Zhang et al.

Summary: This article introduces a fault diagnosis method based on Internet of Ships (IoS) and deep learning (DL), and proposes an adaptive privacy-preserving federated learning approach named AdaPFL. The approach can organize different shipping agents to collaboratively develop a model while protecting the agents' raw information, and adaptively adjust the model aggregation interval using a control algorithm to cope with harsh marine environments.

IEEE INTERNET OF THINGS JOURNAL (2022)

Add to Collection

Article Environmental Sciences

Deep Reinforcement Learning Based Freshness-Aware Path Planning for UAV-Assisted Edge Computing Networks with Device Mobility

Yingsheng Peng et al.

Summary: This paper studies a UAV-assisted mobile edge computing (MEC) network, using the age of information (AoI) as a performance metric. The intelligent and freshness-aware path planning of the UAV is achieved through the deep reinforcement learning (DRL) framework and the double deep Q-learning network (DDQN) algorithm. Simulation results validate the effectiveness of the proposed path planning scheme and reveal the impact of device and UAV speeds on the transmission delay.

REMOTE SENSING (2022)

Add to Collection

Article Computer Science, Information Systems

LEDGE: Leveraging Edge Computing for Resilient Access Management of Mobile IoT

Di Wu et al.

Summary: In response to the challenges posed by IoT devices on mobile access control and monitoring, LEDGE is introduced as a secure and agile software-defined edge computing system. By incorporating efficient location authentication, optimal access point assignment, scalable Personal AP protocol, and anomaly detection through deep learning, LEDGE demonstrates promising results in mobile IoT access management.

IEEE TRANSACTIONS ON MOBILE COMPUTING (2021)

Add to Collection

Article Chemistry, Multidisciplinary

Intelligent Diagnosis of Rotating Machinery Based on Optimized Adaptive Learning Dictionary and 1DCNN

Hongchao Wang et al.

Summary: This paper proposes an intelligent fault diagnosis method for rotating machinery based on an optimized adaptive learning dictionary and one-dimensional convolutional neural network (1DCNN). By constructing a redundant dictionary, solving sparse coefficients, training the 1DCNN model, the method achieves higher accuracy and better generalization ability in fault classification diagnosis compared to other models under different datasets.

APPLIED SCIENCES-BASEL (2021)

Add to Collection

Article Automation & Control Systems

Deep Reinforcement Learning Based Computation Offloading in Fog Enabled Industrial Internet of Things

Yijing Ren et al.

Summary: This article proposes a deep reinforcement learning-based approach to minimize long-term system energy consumption in a computation offloading scenario with multiple IIoT devices and multiple F-APs. The proposal features a multi-agent setting and offline training to successfully address the complexity issue in traditional methods, achieving optimized interactions between devices and F-APs.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

Add to Collection

Article Engineering, Mechanical

Collaborative deep learning framework for fault diagnosis in distributed complex systems

Haoxiang Wang et al.

Summary: In distributed complex systems, a novel collaborative deep learning framework is proposed, which aims to improve diagnosis accuracy by transmitting latent parameters instead of sharing raw data, demonstrating robustness and adaptability.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

A high-speed D-CART online fault diagnosis algorithm for rotor systems

Huaxia Deng et al.

APPLIED INTELLIGENCE (2020)

Add to Collection

Article Computer Science, Theory & Methods

Optimization of lightweight task offloading strategy for mobile edge computing based on deep reinforcement learning

Haifeng Lu et al.

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE (2020)

Add to Collection

Article Engineering, Mechanical

Reliability of response region: A novel mechanism in visual tracking by edge computing for IIoT environments

Shuai Liu et al.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2020)

Add to Collection

Review Engineering, Mechanical

Applications of machine learning to machine fault diagnosis: A review and roadmap

Yaguo Lei et al.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2020)

Add to Collection

Article Automation & Control Systems

Privacy-Preserving Database Assisted Spectrum Access for Industrial Internet of Things: A Distributed Learning Approach

Mengyuan Zhang et al.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Online Anticipatory Proactive Network Association in Mobile Edge Computing for IoT

Qimei Cui et al.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2020)

Add to Collection

Review Computer Science, Information Systems

Toward Edge Intelligence: Multiaccess Edge Computing for 5G and Internet of Things

Yaqiong Liu et al.

IEEE INTERNET OF THINGS JOURNAL (2020)

Add to Collection

Article Engineering, Mechanical

Intelligent ball screw fault diagnosis using a deep domain adaptation methodology

Moslem Azamfar et al.

MECHANISM AND MACHINE THEORY (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Deep reinforcement learning based mobile edge computing for intelligent Internet of Things

Rui Zhao et al.

PHYSICAL COMMUNICATION (2020)

Add to Collection

Article Computer Science, Information Systems

Dynamic Computation Offloading With Energy Harvesting Devices: A Hybrid-Decision-Based Deep Reinforcement Learning Approach

Jing Zhang et al.

IEEE INTERNET OF THINGS JOURNAL (2020)

Add to Collection

Article Computer Science, Information Systems

Optimal Joint Scheduling and Cloud Offloading for Mobile Applications

S. Eman Mahmoodi et al.

IEEE TRANSACTIONS ON CLOUD COMPUTING (2019)

Add to Collection

Article Engineering, Electrical & Electronic

Learning-Based Computation Offloading for IoT Devices With Energy Harvesting

Minghui Min et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2019)

Add to Collection

Article Automation & Control Systems

Fault Detection and Isolation in Industrial Processes Using Deep Learning Approaches

Rahat Iqbal et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2019)

Add to Collection

Article Computer Science, Information Systems

Dynamic Edge Computation Offloading for Internet of Things With Energy Harvesting: A Learning Method

Ziling Wei et al.

IEEE INTERNET OF THINGS JOURNAL (2019)

Add to Collection

Article Automation & Control Systems

A Novel Deep Learning Network via Multiscale Inner Product With Locally Connected Feature Extraction for Intelligent Fault Detection

Tongyang Pan et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2019)

Add to Collection

Article Engineering, Electrical & Electronic

Mobility-Aware Edge Caching and Computing in Vehicle Networks: A Deep Reinforcement Learning

Le Thanh Tan et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2018)

Add to Collection

Article Computer Science, Information Systems

Challenges of Connecting Edge and Cloud Computing: A Security and Forensic Perspective

Christian Esposito et al.

IEEE CLOUD COMPUTING (2017)

Add to Collection

Article Engineering, Electrical & Electronic

Dynamic Computation Offloading for Mobile-Edge Computing With Energy Harvesting Devices

Yuyi Mao et al.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2016)

Add to Collection

Article Engineering, Electrical & Electronic

Communicating While Computing [Distributed mobile cloud computing over 5G heterogeneous networks]

Sergio Barbarossa et al.

IEEE SIGNAL PROCESSING MAGAZINE (2014)

Add to Collection

Article Engineering, Electrical & Electronic

Energy-Optimal Mobile Cloud Computing under Stochastic Wireless Channel

Weiwen Zhang et al.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2013)

Add to Collection

Article Computer Science, Hardware & Architecture

A Survey of Computation Offloading for Mobile Systems

Karthik Kumar et al.

MOBILE NETWORKS & APPLICATIONS (2013)

Add to Collection

© Peeref 2019-2024. All rights reserved.